Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add D-Robotics/moss --skill rdk-embodied-lerobotgit clone --depth 1 https://github.com/D-Robotics/mossWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/d-robotics/moss/rdk-embodied-lerobot)<a href="https://agentmods.dev/skills/d-robotics/moss/rdk-embodied-lerobot"><img src="https://agentmods.dev/badge/skills/d-robotics/moss/rdk-embodied-lerobot/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/d-robotics/moss/rdk-embodied-lerobot"><img src="https://agentmods.dev/badge/skills/d-robotics/moss/rdk-embodied-lerobot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 90 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00297 | $0.03677 |
| Opus 5 | $0.00148 | $0.01839 |
| Sonnet 5 | $0.00059 | $0.00735 |
| Haiku 4.5 | $0.00030 | $0.00368 |
Grade A, and why
rdk-embodied-lerobot scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RDK Embodied AI: LeRobot ACT & Pi0 VLA Deployment
Take a trained robot-control policy and run it on an RDK board's BPU: a LeRobot ACT imitation policy, or a Pi0 / openpi VLA model. This skill owns the software deployment half only — exporting a checkpoint to ONNX, compiling it to .hbm in the OpenExplorer (OE) Docker toolchain, and running the on-board control loop.
The single most important thing: a board can only run an OE-compiled .hbm. It cannot run a raw .pt/ONNX policy, and the on-board control script (bpu_control_robot.py) loads .hbm + .npy normalization files, never the PyTorch checkpoint. If the user copied a checkpoint to the board expecting it to drive the arm, stop and route them through the export→compile loop first.
Sources: official D-Robotics repos rdk_LeRobot_tools (
stable/s100/s600branches), openpi_runtime (develop), huggingface.co/D-Robotics/openpi. Every non-trivial claim below is verified against those READMEs/scripts.
Scope boundary — read this before answering
This skill covers trained policy → BPU → on-board control loop ONLY.
- ✅ In scope: export ACT to ONNX, compile to
.hbm, board-sidehbm-runtime/ C++ BPU runtime,bpu_control_robot.py, Pi0 client-server runtime. - ❌ Out of scope (it's upstream LeRobot, not this repo): SO-101/SO-100 arm assembly, motor ID setup, zero-point calibration (
lerobot-calibrate), teleoperation data collection (lerobot-record), ACT training (lerobot-train), serial ports/baud. Point the user to huggingface/lerobot and the SO-101 docs for that front half.
Which path / which branch (decision cheat-sheet)
Pick the path first, then the branch — they pin different LeRobot versions and toolchain settings.
| Goal | Path | Repo + branch | Board | march |
LeRobot |
|---|---|---|---|---|---|
| ACT on S100, current | ACT | rdk_LeRobot_tools s100 |
S100 (Nash-e) | nash-e |
upstream HF v0.5.2 |
| ACT on S600, current | ACT | rdk_LeRobot_tools s600 |
S600 (Nash) | nash-p |
upstream HF v0.5.2 |
| ACT, legacy v2.1 datasets | ACT | rdk_LeRobot_tools stable |
S100 | nash-e |
D-Robotics fork |
| Pi0 VLA dual-arm | VLA | openpi_runtime develop |
S600 (Nash) | (pre-quantized HBM) | n/a |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 119 lines · 297 tokens per session scan A e4604b0aae4a
rdk-embodied-lerobot is a skill published in the GitHub repository D-Robotics/moss (142 stars, last pushed 14d ago), licensed MIT. It adds 297 tokens to every session and 3,677 once invoked, about $0.0015 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
spark-environment-setup
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.
spark-memory-thermal-ops
Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
llama-cpp
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
minicpm5-deploy-vllm-ascend
Deploy MiniCPM5-2B with vLLM on Huawei Ascend NPU using vLLM-Ascend. Use when the user mentions vLLM-Ascend, Ascend NPU, Huawei Ascend, CANN, torchnpu, davinci devices, or wants an OpenAI-compatible MiniCPM5 server on Ascend hardware.
amc-run-rtsp-calibration
Calibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API. Use when the user provides RTSP URLs or asks to calibrate live cameras; VIOS records clips, AMC ingests them, then runs calibration.